diff options
Diffstat (limited to 'fs/proc')
-rw-r--r-- | fs/proc/Makefile | 2 | ||||
-rw-r--r-- | fs/proc/array.c | 40 | ||||
-rw-r--r-- | fs/proc/base.c | 391 | ||||
-rw-r--r-- | fs/proc/cmdline.c | 2 | ||||
-rw-r--r-- | fs/proc/consoles.c | 2 | ||||
-rw-r--r-- | fs/proc/cpuinfo.c | 2 | ||||
-rw-r--r-- | fs/proc/devices.c | 2 | ||||
-rw-r--r-- | fs/proc/fd.c | 8 | ||||
-rw-r--r-- | fs/proc/generic.c | 35 | ||||
-rw-r--r-- | fs/proc/inode.c | 11 | ||||
-rw-r--r-- | fs/proc/internal.h | 27 | ||||
-rw-r--r-- | fs/proc/interrupts.c | 2 | ||||
-rw-r--r-- | fs/proc/kcore.c | 8 | ||||
-rw-r--r-- | fs/proc/kmsg.c | 2 | ||||
-rw-r--r-- | fs/proc/loadavg.c | 2 | ||||
-rw-r--r-- | fs/proc/meminfo.c | 41 | ||||
-rw-r--r-- | fs/proc/namespaces.c | 14 | ||||
-rw-r--r-- | fs/proc/nommu.c | 2 | ||||
-rw-r--r-- | fs/proc/page.c | 12 | ||||
-rw-r--r-- | fs/proc/proc_devtree.c | 240 | ||||
-rw-r--r-- | fs/proc/proc_net.c | 4 | ||||
-rw-r--r-- | fs/proc/proc_sysctl.c | 2 | ||||
-rw-r--r-- | fs/proc/proc_tty.c | 4 | ||||
-rw-r--r-- | fs/proc/root.c | 12 | ||||
-rw-r--r-- | fs/proc/self.c | 2 | ||||
-rw-r--r-- | fs/proc/softirqs.c | 2 | ||||
-rw-r--r-- | fs/proc/stat.c | 26 | ||||
-rw-r--r-- | fs/proc/task_mmu.c | 397 | ||||
-rw-r--r-- | fs/proc/task_nommu.c | 88 | ||||
-rw-r--r-- | fs/proc/thread_self.c | 85 | ||||
-rw-r--r-- | fs/proc/uptime.c | 4 | ||||
-rw-r--r-- | fs/proc/version.c | 2 | ||||
-rw-r--r-- | fs/proc/vmcore.c | 111 |
33 files changed, 760 insertions, 824 deletions
diff --git a/fs/proc/Makefile b/fs/proc/Makefile index ab30716584f5..7151ea428041 100644 --- a/fs/proc/Makefile +++ b/fs/proc/Makefile @@ -23,10 +23,10 @@ proc-y += version.o proc-y += softirqs.o proc-y += namespaces.o proc-y += self.o +proc-y += thread_self.o proc-$(CONFIG_PROC_SYSCTL) += proc_sysctl.o proc-$(CONFIG_NET) += proc_net.o proc-$(CONFIG_PROC_KCORE) += kcore.o proc-$(CONFIG_PROC_VMCORE) += vmcore.o -proc-$(CONFIG_PROC_DEVICETREE) += proc_devtree.o proc-$(CONFIG_PRINTK) += kmsg.o proc-$(CONFIG_PROC_PAGE_MONITOR) += page.o diff --git a/fs/proc/array.c b/fs/proc/array.c index 1bd2077187fd..cd3653e4f35c 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -138,26 +138,17 @@ static const char * const task_state_array[] = { "D (disk sleep)", /* 2 */ "T (stopped)", /* 4 */ "t (tracing stop)", /* 8 */ - "Z (zombie)", /* 16 */ - "X (dead)", /* 32 */ - "x (dead)", /* 64 */ - "K (wakekill)", /* 128 */ - "W (waking)", /* 256 */ - "P (parked)", /* 512 */ + "X (dead)", /* 16 */ + "Z (zombie)", /* 32 */ }; static inline const char *get_task_state(struct task_struct *tsk) { - unsigned int state = (tsk->state & TASK_REPORT) | tsk->exit_state; - const char * const *p = &task_state_array[0]; + unsigned int state = (tsk->state | tsk->exit_state) & TASK_REPORT; - BUILD_BUG_ON(1 + ilog2(TASK_STATE_MAX) != ARRAY_SIZE(task_state_array)); + BUILD_BUG_ON(1 + ilog2(TASK_REPORT) != ARRAY_SIZE(task_state_array)-1); - while (state) { - p++; - state >>= 1; - } - return *p; + return task_state_array[fls(state)]; } static inline void task_state(struct seq_file *m, struct pid_namespace *ns, @@ -306,15 +297,11 @@ static void render_cap_t(struct seq_file *m, const char *header, seq_puts(m, header); CAP_FOR_EACH_U32(__capi) { seq_printf(m, "%08x", - a->cap[(_KERNEL_CAPABILITY_U32S-1) - __capi]); + a->cap[CAP_LAST_U32 - __capi]); } seq_putc(m, '\n'); } -/* Remove non-existent capabilities */ -#define NORM_CAPS(v) (v.cap[CAP_TO_INDEX(CAP_LAST_CAP)] &= \ - CAP_TO_MASK(CAP_LAST_CAP + 1) - 1) - static inline void task_cap(struct seq_file *m, struct task_struct *p) { const struct cred *cred; @@ -328,11 +315,6 @@ static inline void task_cap(struct seq_file *m, struct task_struct *p) cap_bset = cred->cap_bset; rcu_read_unlock(); - NORM_CAPS(cap_inheritable); - NORM_CAPS(cap_permitted); - NORM_CAPS(cap_effective); - NORM_CAPS(cap_bset); - render_cap_t(m, "CapInh:\t", &cap_inheritable); render_cap_t(m, "CapPrm:\t", &cap_permitted); render_cap_t(m, "CapEff:\t", &cap_effective); @@ -453,8 +435,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, min_flt += t->min_flt; maj_flt += t->maj_flt; gtime += task_gtime(t); - t = next_thread(t); - } while (t != task); + } while_each_thread(task, t); min_flt += sig->min_flt; maj_flt += sig->maj_flt; @@ -483,13 +464,8 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, priority = task_prio(task); nice = task_nice(task); - /* Temporary variable needed for gcc-2.96 */ - /* convert timespec -> nsec*/ - start_time = - (unsigned long long)task->real_start_time.tv_sec * NSEC_PER_SEC - + task->real_start_time.tv_nsec; /* convert nsec -> ticks */ - start_time = nsec_to_clock_t(start_time); + start_time = nsec_to_clock_t(task->real_start_time); seq_printf(m, "%d (%s) %c", pid_nr_ns(pid, ns), tcomm, state); seq_put_decimal_ll(m, ' ', ppid); diff --git a/fs/proc/base.c b/fs/proc/base.c index 03c8d747be48..950100e326a1 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -105,7 +105,7 @@ */ struct pid_entry { - char *name; + const char *name; int len; umode_t mode; const struct inode_operations *iop; @@ -130,10 +130,6 @@ struct pid_entry { { .proc_get_link = get_link } ) #define REG(NAME, MODE, fops) \ NOD(NAME, (S_IFREG|(MODE)), NULL, &fops, {}) -#define INF(NAME, MODE, read) \ - NOD(NAME, (S_IFREG|(MODE)), \ - NULL, &proc_info_file_operations, \ - { .proc_read = read } ) #define ONE(NAME, MODE, show) \ NOD(NAME, (S_IFREG|(MODE)), \ NULL, &proc_single_file_operations, \ @@ -200,59 +196,32 @@ static int proc_root_link(struct dentry *dentry, struct path *path) return result; } -static int proc_pid_cmdline(struct task_struct *task, char * buffer) +static int proc_pid_cmdline(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *task) { - int res = 0; - unsigned int len; - struct mm_struct *mm = get_task_mm(task); - if (!mm) - goto out; - if (!mm->arg_end) - goto out_mm; /* Shh! No looking before we're done */ - - len = mm->arg_end - mm->arg_start; - - if (len > PAGE_SIZE) - len = PAGE_SIZE; - - res = access_process_vm(task, mm->arg_start, buffer, len, 0); - - // If the nul at the end of args has been overwritten, then - // assume application is using setproctitle(3). - if (res > 0 && buffer[res-1] != '\0' && len < PAGE_SIZE) { - len = strnlen(buffer, res); - if (len < res) { - res = len; - } else { - len = mm->env_end - mm->env_start; - if (len > PAGE_SIZE - res) - len = PAGE_SIZE - res; - res += access_process_vm(task, mm->env_start, buffer+res, len, 0); - res = strnlen(buffer, res); - } - } -out_mm: - mmput(mm); -out: - return res; + /* + * Rely on struct seq_operations::show() being called once + * per internal buffer allocation. See single_open(), traverse(). + */ + BUG_ON(m->size < PAGE_SIZE); + m->count += get_cmdline(task, m->buf, PAGE_SIZE); + return 0; } -static int proc_pid_auxv(struct task_struct *task, char *buffer) +static int proc_pid_auxv(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *task) { struct mm_struct *mm = mm_access(task, PTRACE_MODE_READ); - int res = PTR_ERR(mm); if (mm && !IS_ERR(mm)) { unsigned int nwords = 0; do { nwords += 2; } while (mm->saved_auxv[nwords - 2] != 0); /* AT_NULL */ - res = nwords * sizeof(mm->saved_auxv[0]); - if (res > PAGE_SIZE) - res = PAGE_SIZE; - memcpy(buffer, mm->saved_auxv, res); + seq_write(m, mm->saved_auxv, nwords * sizeof(mm->saved_auxv[0])); mmput(mm); - } - return res; + return 0; + } else + return PTR_ERR(mm); } @@ -261,7 +230,8 @@ static int proc_pid_auxv(struct task_struct *task, char *buffer) * Provides a wchan file via kallsyms in a proper one-value-per-file format. * Returns the resolved symbol. If that fails, simply return the address. */ -static int proc_pid_wchan(struct task_struct *task, char *buffer) +static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *task) { unsigned long wchan; char symname[KSYM_NAME_LEN]; @@ -272,9 +242,9 @@ static int proc_pid_wchan(struct task_struct *task, char *buffer) if (!ptrace_may_access(task, PTRACE_MODE_READ)) return 0; else - return sprintf(buffer, "%lu", wchan); + return seq_printf(m, "%lu", wchan); else - return sprintf(buffer, "%s", symname); + return seq_printf(m, "%s", symname); } #endif /* CONFIG_KALLSYMS */ @@ -336,9 +306,10 @@ static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns, /* * Provides /proc/PID/schedstat */ -static int proc_pid_schedstat(struct task_struct *task, char *buffer) +static int proc_pid_schedstat(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *task) { - return sprintf(buffer, "%llu %llu %lu\n", + return seq_printf(m, "%llu %llu %lu\n", (unsigned long long)task->se.sum_exec_runtime, (unsigned long long)task->sched_info.run_delay, task->sched_info.pcount); @@ -405,38 +376,8 @@ static const struct file_operations proc_lstats_operations = { #endif -#ifdef CONFIG_CGROUPS -static int cgroup_open(struct inode *inode, struct file *file) -{ - struct pid *pid = PROC_I(inode)->pid; - return single_open(file, proc_cgroup_show, pid); -} - -static const struct file_operations proc_cgroup_operations = { - .open = cgroup_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; -#endif - -#ifdef CONFIG_PROC_PID_CPUSET - -static int cpuset_open(struct inode *inode, struct file *file) -{ - struct pid *pid = PROC_I(inode)->pid; - return single_open(file, proc_cpuset_show, pid); -} - -static const struct file_operations proc_cpuset_operations = { - .open = cpuset_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; -#endif - -static int proc_oom_score(struct task_struct *task, char *buffer) +static int proc_oom_score(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *task) { unsigned long totalpages = totalram_pages + total_swap_pages; unsigned long points = 0; @@ -446,12 +387,12 @@ static int proc_oom_score(struct task_struct *task, char *buffer) points = oom_badness(task, NULL, NULL, totalpages) * 1000 / totalpages; read_unlock(&tasklist_lock); - return sprintf(buffer, "%lu\n", points); + return seq_printf(m, "%lu\n", points); } struct limit_names { - char *name; - char *unit; + const char *name; + const char *unit; }; static const struct limit_names lnames[RLIM_NLIMITS] = { @@ -474,12 +415,11 @@ static const struct limit_names lnames[RLIM_NLIMITS] = { }; /* Display limits for a process */ -static int proc_pid_limits(struct task_struct *task, char *buffer) +static int proc_pid_limits(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *task) { unsigned int i; - int count = 0; unsigned long flags; - char *bufptr = buffer; struct rlimit rlim[RLIM_NLIMITS]; @@ -491,35 +431,34 @@ static int proc_pid_limits(struct task_struct *task, char *buffer) /* * print the file header */ - count += sprintf(&bufptr[count], "%-25s %-20s %-20s %-10s\n", + seq_printf(m, "%-25s %-20s %-20s %-10s\n", "Limit", "Soft Limit", "Hard Limit", "Units"); for (i = 0; i < RLIM_NLIMITS; i++) { if (rlim[i].rlim_cur == RLIM_INFINITY) - count += sprintf(&bufptr[count], "%-25s %-20s ", + seq_printf(m, "%-25s %-20s ", lnames[i].name, "unlimited"); else - count += sprintf(&bufptr[count], "%-25s %-20lu ", + seq_printf(m, "%-25s %-20lu ", lnames[i].name, rlim[i].rlim_cur); if (rlim[i].rlim_max == RLIM_INFINITY) - count += sprintf(&bufptr[count], "%-20s ", "unlimited"); + seq_printf(m, "%-20s ", "unlimited"); else - count += sprintf(&bufptr[count], "%-20lu ", - rlim[i].rlim_max); + seq_printf(m, "%-20lu ", rlim[i].rlim_max); if (lnames[i].unit) - count += sprintf(&bufptr[count], "%-10s\n", - lnames[i].unit); + seq_printf(m, "%-10s\n", lnames[i].unit); else - count += sprintf(&bufptr[count], "\n"); + seq_putc(m, '\n'); } - return count; + return 0; } #ifdef CONFIG_HAVE_ARCH_TRACEHOOK -static int proc_pid_syscall(struct task_struct *task, char *buffer) +static int proc_pid_syscall(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *task) { long nr; unsigned long args[6], sp, pc; @@ -528,11 +467,11 @@ static int proc_pid_syscall(struct task_struct *task, char *buffer) return res; if (task_current_syscall(task, &nr, args, 6, &sp, &pc)) - res = sprintf(buffer, "running\n"); + seq_puts(m, "running\n"); else if (nr < 0) - res = sprintf(buffer, "%ld 0x%lx 0x%lx\n", nr, sp, pc); + seq_printf(m, "%ld 0x%lx 0x%lx\n", nr, sp, pc); else - res = sprintf(buffer, + seq_printf(m, "%ld 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx\n", nr, args[0], args[1], args[2], args[3], args[4], args[5], @@ -630,43 +569,6 @@ static const struct inode_operations proc_def_inode_operations = { .setattr = proc_setattr, }; -#define PROC_BLOCK_SIZE (3*1024) /* 4K page size but our output routines use some slack for overruns */ - -static ssize_t proc_info_read(struct file * file, char __user * buf, - size_t count, loff_t *ppos) -{ - struct inode * inode = file_inode(file); - unsigned long page; - ssize_t length; - struct task_struct *task = get_proc_task(inode); - - length = -ESRCH; - if (!task) - goto out_no_task; - - if (count > PROC_BLOCK_SIZE) - count = PROC_BLOCK_SIZE; - - length = -ENOMEM; - if (!(page = __get_free_page(GFP_TEMPORARY))) - goto out; - - length = PROC_I(inode)->op.proc_read(task, (char*)page); - - if (length >= 0) - length = simple_read_from_buffer(buf, count, ppos, (char *)page, length); - free_page(page); -out: - put_task_struct(task); -out_no_task: - return length; -} - -static const struct file_operations proc_info_file_operations = { - .read = proc_info_read, - .llseek = generic_file_llseek, -}; - static int proc_single_show(struct seq_file *m, void *v) { struct inode *inode = m->private; @@ -699,29 +601,35 @@ static const struct file_operations proc_single_file_operations = { .release = single_release, }; -static int __mem_open(struct inode *inode, struct file *file, unsigned int mode) + +struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode) { - struct task_struct *task = get_proc_task(file_inode(file)); - struct mm_struct *mm; + struct task_struct *task = get_proc_task(inode); + struct mm_struct *mm = ERR_PTR(-ESRCH); - if (!task) - return -ESRCH; + if (task) { + mm = mm_access(task, mode); + put_task_struct(task); - mm = mm_access(task, mode); - put_task_struct(task); + if (!IS_ERR_OR_NULL(mm)) { + /* ensure this mm_struct can't be freed */ + atomic_inc(&mm->mm_count); + /* but do not pin its memory */ + mmput(mm); + } + } + + return mm; +} + +static int __mem_open(struct inode *inode, struct file *file, unsigned int mode) +{ + struct mm_struct *mm = proc_mem_open(inode, mode); if (IS_ERR(mm)) return PTR_ERR(mm); - if (mm) { - /* ensure this mm_struct can't be freed */ - atomic_inc(&mm->mm_count); - /* but do not pin its memory */ - mmput(mm); - } - file->private_data = mm; - return 0; } @@ -1236,6 +1144,9 @@ static ssize_t proc_fault_inject_write(struct file * file, make_it_fail = simple_strtol(strstrip(buffer), &end, 0); if (*end) return -EINVAL; + if (make_it_fail < 0 || make_it_fail > 1) + return -EINVAL; + task = get_proc_task(file_inode(file)); if (!task) return -ESRCH; @@ -1658,13 +1569,18 @@ int pid_revalidate(struct dentry *dentry, unsigned int flags) return 0; } +static inline bool proc_inode_is_dead(struct inode *inode) +{ + return !proc_pid(inode)->tasks[PIDTYPE_PID].first; +} + int pid_delete_dentry(const struct dentry *dentry) { /* Is the task we represent dead? * If so, then don't put the dentry on the lru list, * kill it immediately. */ - return !proc_pid(dentry->d_inode)->tasks[PIDTYPE_PID].first; + return proc_inode_is_dead(dentry->d_inode); } const struct dentry_operations pid_dentry_operations = @@ -1819,6 +1735,7 @@ static int proc_map_files_get_link(struct dentry *dentry, struct path *path) if (rc) goto out_mmput; + rc = -ENOENT; down_read(&mm->mmap_sem); vma = find_exact_vma(mm, vm_start, vm_end); if (vma && vma->vm_file) { @@ -2079,7 +1996,7 @@ static int show_timer(struct seq_file *m, void *v) struct k_itimer *timer; struct timers_private *tp = m->private; int notify; - static char *nstr[] = { + static const char * const nstr[] = { [SIGEV_SIGNAL] = "signal", [SIGEV_NONE] = "none", [SIGEV_THREAD] = "thread", @@ -2415,7 +2332,7 @@ static const struct file_operations proc_coredump_filter_operations = { #endif #ifdef CONFIG_TASK_IO_ACCOUNTING -static int do_io_accounting(struct task_struct *task, char *buffer, int whole) +static int do_io_accounting(struct task_struct *task, struct seq_file *m, int whole) { struct task_io_accounting acct = task->ioac; unsigned long flags; @@ -2439,7 +2356,7 @@ static int do_io_accounting(struct task_struct *task, char *buffer, int whole) unlock_task_sighand(task, &flags); } - result = sprintf(buffer, + result = seq_printf(m, "rchar: %llu\n" "wchar: %llu\n" "syscr: %llu\n" @@ -2459,20 +2376,22 @@ out_unlock: return result; } -static int proc_tid_io_accounting(struct task_struct *task, char *buffer) +static int proc_tid_io_accounting(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *task) { - return do_io_accounting(task, buffer, 0); + return do_io_accounting(task, m, 0); } -static int proc_tgid_io_accounting(struct task_struct *task, char *buffer) +static int proc_tgid_io_accounting(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *task) { - return do_io_accounting(task, buffer, 1); + return do_io_accounting(task, m, 1); } #endif /* CONFIG_TASK_IO_ACCOUNTING */ #ifdef CONFIG_USER_NS static int proc_id_map_open(struct inode *inode, struct file *file, - struct seq_operations *seq_ops) + const struct seq_operations *seq_ops) { struct user_namespace *ns = NULL; struct task_struct *task; @@ -2580,10 +2499,10 @@ static const struct pid_entry tgid_base_stuff[] = { DIR("net", S_IRUGO|S_IXUGO, proc_net_inode_operations, proc_net_operations), #endif REG("environ", S_IRUSR, proc_environ_operations), - INF("auxv", S_IRUSR, proc_pid_auxv), + ONE("auxv", S_IRUSR, proc_pid_auxv), ONE("status", S_IRUGO, proc_pid_status), - ONE("personality", S_IRUGO, proc_pid_personality), - INF("limits", S_IRUGO, proc_pid_limits), + ONE("personality", S_IRUSR, proc_pid_personality), + ONE("limits", S_IRUGO, proc_pid_limits), #ifdef CONFIG_SCHED_DEBUG REG("sched", S_IRUGO|S_IWUSR, proc_pid_sched_operations), #endif @@ -2592,9 +2511,9 @@ static const struct pid_entry tgid_base_stuff[] = { #endif REG("comm", S_IRUGO|S_IWUSR, proc_pid_set_comm_operations), #ifdef CONFIG_HAVE_ARCH_TRACEHOOK - INF("syscall", S_IRUGO, proc_pid_syscall), + ONE("syscall", S_IRUSR, proc_pid_syscall), #endif - INF("cmdline", S_IRUGO, proc_pid_cmdline), + ONE("cmdline", S_IRUGO, proc_pid_cmdline), ONE("stat", S_IRUGO, proc_tgid_stat), ONE("statm", S_IRUGO, proc_pid_statm), REG("maps", S_IRUGO, proc_pid_maps_operations), @@ -2611,30 +2530,30 @@ static const struct pid_entry tgid_base_stuff[] = { #ifdef CONFIG_PROC_PAGE_MONITOR REG("clear_refs", S_IWUSR, proc_clear_refs_operations), REG("smaps", S_IRUGO, proc_pid_smaps_operations), - REG("pagemap", S_IRUGO, proc_pagemap_operations), + REG("pagemap", S_IRUSR, proc_pagemap_operations), #endif #ifdef CONFIG_SECURITY DIR("attr", S_IRUGO|S_IXUGO, proc_attr_dir_inode_operations, proc_attr_dir_operations), #endif #ifdef CONFIG_KALLSYMS - INF("wchan", S_IRUGO, proc_pid_wchan), + ONE("wchan", S_IRUGO, proc_pid_wchan), #endif #ifdef CONFIG_STACKTRACE - ONE("stack", S_IRUGO, proc_pid_stack), + ONE("stack", S_IRUSR, proc_pid_stack), #endif #ifdef CONFIG_SCHEDSTATS - INF("schedstat", S_IRUGO, proc_pid_schedstat), + ONE("schedstat", S_IRUGO, proc_pid_schedstat), #endif #ifdef CONFIG_LATENCYTOP REG("latency", S_IRUGO, proc_lstats_operations), #endif #ifdef CONFIG_PROC_PID_CPUSET - REG("cpuset", S_IRUGO, proc_cpuset_operations), + ONE("cpuset", S_IRUGO, proc_cpuset_show), #endif #ifdef CONFIG_CGROUPS - REG("cgroup", S_IRUGO, proc_cgroup_operations), + ONE("cgroup", S_IRUGO, proc_cgroup_show), #endif - INF("oom_score", S_IRUGO, proc_oom_score), + ONE("oom_score", S_IRUGO, proc_oom_score), REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations), REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations), #ifdef CONFIG_AUDITSYSCALL @@ -2648,10 +2567,10 @@ static const struct pid_entry tgid_base_stuff[] = { REG("coredump_filter", S_IRUGO|S_IWUSR, proc_coredump_filter_operations), #endif #ifdef CONFIG_TASK_IO_ACCOUNTING - INF("io", S_IRUSR, proc_tgid_io_accounting), + ONE("io", S_IRUSR, proc_tgid_io_accounting), #endif #ifdef CONFIG_HARDWALL - INF("hardwall", S_IRUGO, proc_pid_hardwall), + ONE("hardwall", S_IRUGO, proc_pid_hardwall), #endif #ifdef CONFIG_USER_NS REG("uid_map", S_IRUGO|S_IWUSR, proc_uid_map_operations), @@ -2803,12 +2722,12 @@ out: struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags) { - int result = 0; + int result = -ENOENT; struct task_struct *task; unsigned tgid; struct pid_namespace *ns; - tgid = name_to_int(dentry); + tgid = name_to_int(&dentry->d_name); if (tgid == ~0U) goto out; @@ -2870,7 +2789,7 @@ retry: return iter; } -#define TGID_OFFSET (FIRST_PROCESS_ENTRY + 1) +#define TGID_OFFSET (FIRST_PROCESS_ENTRY + 2) /* for the /proc/ directory itself, after non-process stuff has been done */ int proc_pid_readdir(struct file *file, struct dir_context *ctx) @@ -2882,14 +2801,19 @@ int proc_pid_readdir(struct file *file, struct dir_context *ctx) if (pos >= PID_MAX_LIMIT + TGID_OFFSET) return 0; - if (pos == TGID_OFFSET - 1) { + if (pos == TGID_OFFSET - 2) { struct inode *inode = ns->proc_self->d_inode; if (!dir_emit(ctx, "self", 4, inode->i_ino, DT_LNK)) return 0; - iter.tgid = 0; - } else { - iter.tgid = pos - TGID_OFFSET; + ctx->pos = pos = pos + 1; + } + if (pos == TGID_OFFSET - 1) { + struct inode *inode = ns->proc_thread_self->d_inode; + if (!dir_emit(ctx, "thread-self", 11, inode->i_ino, DT_LNK)) + return 0; + ctx->pos = pos = pos + 1; } + iter.tgid = pos - TGID_OFFSET; iter.task = NULL; for (iter = next_tgid(ns, iter); iter.task; @@ -2918,19 +2842,22 @@ static const struct pid_entry tid_base_stuff[] = { DIR("fd", S_IRUSR|S_IXUSR, proc_fd_inode_operations, proc_fd_operations), DIR("fdinfo", S_IRUSR|S_IXUSR, proc_fdinfo_inode_operations, proc_fdinfo_operations), DIR("ns", S_IRUSR|S_IXUGO, proc_ns_dir_inode_operations, proc_ns_dir_operations), +#ifdef CONFIG_NET + DIR("net", S_IRUGO|S_IXUGO, proc_net_inode_operations, proc_net_operations), +#endif REG("environ", S_IRUSR, proc_environ_operations), - INF("auxv", S_IRUSR, proc_pid_auxv), + ONE("auxv", S_IRUSR, proc_pid_auxv), ONE("status", S_IRUGO, proc_pid_status), - ONE("personality", S_IRUGO, proc_pid_personality), - INF("limits", S_IRUGO, proc_pid_limits), + ONE("personality", S_IRUSR, proc_pid_personality), + ONE("limits", S_IRUGO, proc_pid_limits), #ifdef CONFIG_SCHED_DEBUG REG("sched", S_IRUGO|S_IWUSR, proc_pid_sched_operations), #endif REG("comm", S_IRUGO|S_IWUSR, proc_pid_set_comm_operations), #ifdef CONFIG_HAVE_ARCH_TRACEHOOK - INF("syscall", S_IRUGO, proc_pid_syscall), + ONE("syscall", S_IRUSR, proc_pid_syscall), #endif - INF("cmdline", S_IRUGO, proc_pid_cmdline), + ONE("cmdline", S_IRUGO, proc_pid_cmdline), ONE("stat", S_IRUGO, proc_tid_stat), ONE("statm", S_IRUGO, proc_pid_statm), REG("maps", S_IRUGO, proc_tid_maps_operations), @@ -2949,30 +2876,30 @@ static const struct pid_entry tid_base_stuff[] = { #ifdef CONFIG_PROC_PAGE_MONITOR REG("clear_refs", S_IWUSR, proc_clear_refs_operations), REG("smaps", S_IRUGO, proc_tid_smaps_operations), - REG("pagemap", S_IRUGO, proc_pagemap_operations), + REG("pagemap", S_IRUSR, proc_pagemap_operations), #endif #ifdef CONFIG_SECURITY DIR("attr", S_IRUGO|S_IXUGO, proc_attr_dir_inode_operations, proc_attr_dir_operations), #endif #ifdef CONFIG_KALLSYMS - INF("wchan", S_IRUGO, proc_pid_wchan), + ONE("wchan", S_IRUGO, proc_pid_wchan), #endif #ifdef CONFIG_STACKTRACE - ONE("stack", S_IRUGO, proc_pid_stack), + ONE("stack", S_IRUSR, proc_pid_stack), #endif #ifdef CONFIG_SCHEDSTATS - INF("schedstat", S_IRUGO, proc_pid_schedstat), + ONE("schedstat", S_IRUGO, proc_pid_schedstat), #endif #ifdef CONFIG_LATENCYTOP REG("latency", S_IRUGO, proc_lstats_operations), #endif #ifdef CONFIG_PROC_PID_CPUSET - REG("cpuset", S_IRUGO, proc_cpuset_operations), + ONE("cpuset", S_IRUGO, proc_cpuset_show), #endif #ifdef CONFIG_CGROUPS - REG("cgroup", S_IRUGO, proc_cgroup_operations), + ONE("cgroup", S_IRUGO, proc_cgroup_show), #endif - INF("oom_score", S_IRUGO, proc_oom_score), + ONE("oom_score", S_IRUGO, proc_oom_score), REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations), REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations), #ifdef CONFIG_AUDITSYSCALL @@ -2983,10 +2910,10 @@ static const struct pid_entry tid_base_stuff[] = { REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations), #endif #ifdef CONFIG_TASK_IO_ACCOUNTING - INF("io", S_IRUSR, proc_tid_io_accounting), + ONE("io", S_IRUSR, proc_tid_io_accounting), #endif #ifdef CONFIG_HARDWALL - INF("hardwall", S_IRUGO, proc_pid_hardwall), + ONE("hardwall", S_IRUGO, proc_pid_hardwall), #endif #ifdef CONFIG_USER_NS REG("uid_map", S_IRUGO|S_IWUSR, proc_uid_map_operations), @@ -3056,7 +2983,7 @@ static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry if (!leader) goto out_no_task; - tid = name_to_int(dentry); + tid = name_to_int(&dentry->d_name); if (tid == ~0U) goto out; @@ -3092,34 +3019,42 @@ out_no_task: * In the case of a seek we start with the leader and walk nr * threads past it. */ -static struct task_struct *first_tid(struct task_struct *leader, - int tid, int nr, struct pid_namespace *ns) +static struct task_struct *first_tid(struct pid *pid, int tid, loff_t f_pos, + struct pid_namespace *ns) { - struct task_struct *pos; + struct task_struct *pos, *task; + unsigned long nr = f_pos; + + if (nr != f_pos) /* 32bit overflow? */ + return NULL; rcu_read_lock(); - /* Attempt to start with the pid of a thread */ - if (tid && (nr > 0)) { + task = pid_task(pid, PIDTYPE_PID); + if (!task) + goto fail; + + /* Attempt to start with the tid of a thread */ + if (tid && nr) { pos = find_task_by_pid_ns(tid, ns); - if (pos && (pos->group_leader == leader)) + if (pos && same_thread_group(pos, task)) goto found; } /* If nr exceeds the number of threads there is nothing todo */ - pos = NULL; - if (nr && nr >= get_nr_threads(leader)) - goto out; + if (nr >= get_nr_threads(task)) + goto fail; /* If we haven't found our starting place yet start * with the leader and walk nr threads forward. */ - for (pos = leader; nr > 0; --nr) { - pos = next_thread(pos); - if (pos == leader) { - pos = NULL; - goto out; - } - } + pos = task = task->group_leader; + do { + if (!nr--) + goto found; + } while_each_thread(task, pos); +fail: + pos = NULL; + goto out; found: get_task_struct(pos); out: @@ -3152,25 +3087,16 @@ static struct task_struct *next_tid(struct task_struct *start) /* for the /proc/TGID/task/ directories */ static int proc_task_readdir(struct file *file, struct dir_context *ctx) { - struct task_struct *leader = NULL; - struct task_struct *task = get_proc_task(file_inode(file)); + struct inode *inode = file_inode(file); + struct task_struct *task; struct pid_namespace *ns; int tid; - if (!task) - return -ENOENT; - rcu_read_lock(); - if (pid_alive(task)) { - leader = task->group_leader; - get_task_struct(leader); - } - rcu_read_unlock(); - put_task_struct(task); - if (!leader) + if (proc_inode_is_dead(inode)) return -ENOENT; if (!dir_emit_dots(file, ctx)) - goto out; + return 0; /* f_version caches the tgid value that the last readdir call couldn't * return. lseek aka telldir automagically resets f_version to 0. @@ -3178,7 +3104,7 @@ static int proc_task_readdir(struct file *file, struct dir_context *ctx) ns = file->f_dentry->d_sb->s_fs_info; tid = (int)file->f_version; file->f_version = 0; - for (task = first_tid(leader, tid, ctx->pos - 2, ns); + for (task = first_tid(proc_pid(inode), tid, ctx->pos - 2, ns); task; task = next_tid(task), ctx->pos++) { char name[PROC_NUMBUF]; @@ -3194,8 +3120,7 @@ static int proc_task_readdir(struct file *file, struct dir_context *ctx) break; } } -out: - put_task_struct(leader); + return 0; } diff --git a/fs/proc/cmdline.c b/fs/proc/cmdline.c index 82676e3fcd1d..cbd82dff7e81 100644 --- a/fs/proc/cmdline.c +++ b/fs/proc/cmdline.c @@ -26,4 +26,4 @@ static int __init proc_cmdline_init(void) proc_create("cmdline", 0, NULL, &cmdline_proc_fops); return 0; } -module_init(proc_cmdline_init); +fs_initcall(proc_cmdline_init); diff --git a/fs/proc/consoles.c b/fs/proc/consoles.c index 51942d5abcec..290ba85cb900 100644 --- a/fs/proc/consoles.c +++ b/fs/proc/consoles.c @@ -109,4 +109,4 @@ static int __init proc_consoles_init(void) proc_create("consoles", 0, NULL, &proc_consoles_operations); return 0; } -module_init(proc_consoles_init); +fs_initcall(proc_consoles_init); diff --git a/fs/proc/cpuinfo.c b/fs/proc/cpuinfo.c index 5a1e539a234b..06f4d31e0396 100644 --- a/fs/proc/cpuinfo.c +++ b/fs/proc/cpuinfo.c @@ -21,4 +21,4 @@ static int __init proc_cpuinfo_init(void) proc_create("cpuinfo", 0, NULL, &proc_cpuinfo_operations); return 0; } -module_init(proc_cpuinfo_init); +fs_initcall(proc_cpuinfo_init); diff --git a/fs/proc/devices.c b/fs/proc/devices.c index b14347167c35..50493edc30e5 100644 --- a/fs/proc/devices.c +++ b/fs/proc/devices.c @@ -67,4 +67,4 @@ static int __init proc_devices_init(void) proc_create("devices", 0, NULL, &proc_devinfo_operations); return 0; } -module_init(proc_devices_init); +fs_initcall(proc_devices_init); diff --git a/fs/proc/fd.c b/fs/proc/fd.c index 985ea881b5bc..955bb55fab8c 100644 --- a/fs/proc/fd.c +++ b/fs/proc/fd.c @@ -11,6 +11,7 @@ #include <linux/proc_fs.h> +#include "../mount.h" #include "internal.h" #include "fd.h" @@ -48,8 +49,9 @@ static int seq_show(struct seq_file *m, void *v) } if (!ret) { - seq_printf(m, "pos:\t%lli\nflags:\t0%o\n", - (long long)file->f_pos, f_flags); + seq_printf(m, "pos:\t%lli\nflags:\t0%o\nmnt_id:\t%i\n", + (long long)file->f_pos, f_flags, + real_mount(file->f_path.mnt)->mnt_id); if (file->f_op->show_fdinfo) ret = file->f_op->show_fdinfo(m, file); fput(file); @@ -204,7 +206,7 @@ static struct dentry *proc_lookupfd_common(struct inode *dir, { struct task_struct *task = get_proc_task(dir); int result = -ENOENT; - unsigned fd = name_to_int(dentry); + unsigned fd = name_to_int(&dentry->d_name); if (!task) goto out_no_task; diff --git a/fs/proc/generic.c b/fs/proc/generic.c index cca93b6fb9a9..317b72641ebf 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -27,7 +27,7 @@ #include "internal.h" -DEFINE_SPINLOCK(proc_subdir_lock); +static DEFINE_SPINLOCK(proc_subdir_lock); static int proc_match(unsigned int len, const char *name, struct proc_dir_entry *de) { @@ -49,8 +49,7 @@ static int proc_notify_change(struct dentry *dentry, struct iattr *iattr) setattr_copy(inode, iattr); mark_inode_dirty(inode); - de->uid = inode->i_uid; - de->gid = inode->i_gid; + proc_set_user(de, inode->i_uid, inode->i_gid); de->mode = inode->i_mode; return 0; } @@ -331,28 +330,28 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent, nlink_t nlink) { struct proc_dir_entry *ent = NULL; - const char *fn = name; - unsigned int len; - - /* make sure name is valid */ - if (!name || !strlen(name)) - goto out; + const char *fn; + struct qstr qstr; if (xlate_proc_name(name, parent, &fn) != 0) goto out; + qstr.name = fn; + qstr.len = strlen(fn); + if (qstr.len == 0 || qstr.len >= 256) { + WARN(1, "name len %u\n", qstr.len); + return NULL; + } + if (*parent == &proc_root && name_to_int(&qstr) != ~0U) { + WARN(1, "create '/proc/%s' by hand\n", qstr.name); + return NULL; + } - /* At this point there must not be any '/' characters beyond *fn */ - if (strchr(fn, '/')) - goto out; - - len = strlen(fn); - - ent = kzalloc(sizeof(struct proc_dir_entry) + len + 1, GFP_KERNEL); + ent = kzalloc(sizeof(struct proc_dir_entry) + qstr.len + 1, GFP_KERNEL); if (!ent) goto out; - memcpy(ent->name, fn, len + 1); - ent->namelen = len; + memcpy(ent->name, fn, qstr.len + 1); + ent->namelen = qstr.len; ent->mode = mode; ent->nlink = nlink; atomic_set(&ent->count, 1); diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 124fc43c7090..333080d7a671 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -35,7 +35,7 @@ static void proc_evict_inode(struct inode *inode) const struct proc_ns_operations *ns_ops; void *ns; - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); /* Stop tracking associated processes */ @@ -47,7 +47,7 @@ static void proc_evict_inode(struct inode *inode) pde_put(de); head = PROC_I(inode)->sysctl; if (head) { - rcu_assign_pointer(PROC_I(inode)->sysctl, NULL); + RCU_INIT_POINTER(PROC_I(inode)->sysctl, NULL); sysctl_head_put(head); } /* Release any associated namespace */ @@ -442,6 +442,7 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de) int proc_fill_super(struct super_block *s) { struct inode *root_inode; + int ret; s->s_flags |= MS_NODIRATIME | MS_NOSUID | MS_NOEXEC; s->s_blocksize = 1024; @@ -463,5 +464,9 @@ int proc_fill_super(struct super_block *s) return -ENOMEM; } - return proc_setup_self(s); + ret = proc_setup_self(s); + if (ret) { + return ret; + } + return proc_setup_thread_self(s); } diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 651d09a11dde..aa7a0ee182e1 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -52,7 +52,6 @@ struct proc_dir_entry { union proc_op { int (*proc_get_link)(struct dentry *, struct path *); - int (*proc_read)(struct task_struct *task, char *page); int (*proc_show)(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task); @@ -112,10 +111,10 @@ static inline int task_dumpable(struct task_struct *task) return 0; } -static inline unsigned name_to_int(struct dentry *dentry) +static inline unsigned name_to_int(const struct qstr *qstr) { - const char *name = dentry->d_name.name; - int len = dentry->d_name.len; + const char *name = qstr->name; + int len = qstr->len; unsigned n = 0; if (len > 1 && *name == '0') @@ -178,8 +177,6 @@ extern bool proc_fill_cache(struct file *, struct dir_context *, const char *, i /* * generic.c */ -extern spinlock_t proc_subdir_lock; - extern struct dentry *proc_lookup(struct inode *, struct dentry *, unsigned int); extern struct dentry *proc_lookup_de(struct proc_dir_entry *, struct inode *, struct dentry *); @@ -211,13 +208,6 @@ extern int proc_fill_super(struct super_block *); extern void proc_entry_rundown(struct proc_dir_entry *); /* - * proc_devtree.c - */ -#ifdef CONFIG_PROC_DEVICETREE -extern void proc_device_tree_init(void); -#endif - -/* * proc_namespaces.c */ extern const struct inode_operations proc_ns_dir_inode_operations; @@ -241,6 +231,12 @@ static inline int proc_net_init(void) { return 0; } extern int proc_setup_self(struct super_block *); /* + * proc_thread_self.c + */ +extern int proc_setup_thread_self(struct super_block *); +extern void proc_thread_self_init(void); + +/* * proc_sysctl.c */ #ifdef CONFIG_PROC_SYSCTL @@ -272,8 +268,9 @@ extern int proc_remount(struct super_block *, int *, char *); * task_[no]mmu.c */ struct proc_maps_private { - struct pid *pid; + struct inode *inode; struct task_struct *task; + struct mm_struct *mm; #ifdef CONFIG_MMU struct vm_area_struct *tail_vma; #endif @@ -282,6 +279,8 @@ struct proc_maps_private { #endif }; +struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode); + extern const struct file_operations proc_pid_maps_operations; extern const struct file_operations proc_tid_maps_operations; extern const struct file_operations proc_pid_numa_maps_operations; diff --git a/fs/proc/interrupts.c b/fs/proc/interrupts.c index 05029c0e2f24..a352d5703b41 100644 --- a/fs/proc/interrupts.c +++ b/fs/proc/interrupts.c @@ -50,4 +50,4 @@ static int __init proc_interrupts_init(void) proc_create("interrupts", 0, NULL, &proc_interrupts_operations); return 0; } -module_init(proc_interrupts_init); +fs_initcall(proc_interrupts_init); diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 5ed0e52d6aa0..91a4e6426321 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -172,7 +172,7 @@ get_sparsemem_vmemmap_info(struct kcore_list *ent, struct list_head *head) start = ((unsigned long)pfn_to_page(pfn)) & PAGE_MASK; end = ((unsigned long)pfn_to_page(pfn + nr_pages)) - 1; - end = ALIGN(end, PAGE_SIZE); + end = PAGE_ALIGN(end); /* overlap check (because we have to align page */ list_for_each_entry(tmp, head, list) { if (tmp->type != KCORE_VMEMMAP) @@ -610,8 +610,10 @@ static void __init proc_kcore_text_init(void) struct kcore_list kcore_modules; static void __init add_modules_range(void) { - kclist_add(&kcore_modules, (void *)MODULES_VADDR, + if (MODULES_VADDR != VMALLOC_START && MODULES_END != VMALLOC_END) { + kclist_add(&kcore_modules, (void *)MODULES_VADDR, MODULES_END - MODULES_VADDR, KCORE_VMALLOC); + } } #else static void __init add_modules_range(void) @@ -639,4 +641,4 @@ static int __init proc_kcore_init(void) return 0; } -module_init(proc_kcore_init); +fs_initcall(proc_kcore_init); diff --git a/fs/proc/kmsg.c b/fs/proc/kmsg.c index bdfabdaefdce..05f8dcdb086e 100644 --- a/fs/proc/kmsg.c +++ b/fs/proc/kmsg.c @@ -61,4 +61,4 @@ static int __init proc_kmsg_init(void) proc_create("kmsg", S_IRUSR, NULL, &proc_kmsg_operations); return 0; } -module_init(proc_kmsg_init); +fs_initcall(proc_kmsg_init); diff --git a/fs/proc/loadavg.c b/fs/proc/loadavg.c index 1afa4dd4cae2..aec66e6c2060 100644 --- a/fs/proc/loadavg.c +++ b/fs/proc/loadavg.c @@ -42,4 +42,4 @@ static int __init proc_loadavg_init(void) proc_create("loadavg", 0, NULL, &loadavg_proc_fops); return 0; } -module_init(proc_loadavg_init); +fs_initcall(proc_loadavg_init); diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index a77d2b299199..aa1eee06420f 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -26,7 +26,11 @@ static int meminfo_proc_show(struct seq_file *m, void *v) unsigned long committed; struct vmalloc_info vmi; long cached; + long available; + unsigned long pagecache; + unsigned long wmark_low = 0; unsigned long pages[NR_LRU_LISTS]; + struct zone *zone; int lru; /* @@ -47,12 +51,44 @@ static int meminfo_proc_show(struct seq_file *m, void *v) for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++) pages[lru] = global_page_state(NR_LRU_BASE + lru); + for_each_zone(zone) + wmark_low += zone->watermark[WMARK_LOW]; + + /* + * Estimate the amount of memory available for userspace allocations, + * without causing swapping. + * + * Free memory cannot be taken below the low watermark, before the + * system starts swapping. + */ + available = i.freeram - wmark_low; + + /* + * Not all the page cache can be freed, otherwise the system will + * start swapping. Assume at least half of the page cache, or the + * low watermark worth of cache, needs to stay. + */ + pagecache = pages[LRU_ACTIVE_FILE] + pages[LRU_INACTIVE_FILE]; + pagecache -= min(pagecache / 2, wmark_low); + available += pagecache; + + /* + * Part of the reclaimable slab consists of items that are in use, + * and cannot be freed. Cap this estimate at the low watermark. + */ + available += global_page_state(NR_SLAB_RECLAIMABLE) - + min(global_page_state(NR_SLAB_RECLAIMABLE) / 2, wmark_low); + + if (available < 0) + available = 0; + /* * Tagged format, for easy grepping and expansion. */ seq_printf(m, "MemTotal: %8lu kB\n" "MemFree: %8lu kB\n" + "MemAvailable: %8lu kB\n" "Buffers: %8lu kB\n" "Cached: %8lu kB\n" "SwapCached: %8lu kB\n" @@ -105,6 +141,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) , K(i.totalram), K(i.freeram), + K(available), K(i.bufferram), K(cached), K(total_swapcache_pages()), @@ -131,7 +168,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) K(global_page_state(NR_WRITEBACK)), K(global_page_state(NR_ANON_PAGES)), K(global_page_state(NR_FILE_MAPPED)), - K(global_page_state(NR_SHMEM)), + K(i.sharedram), K(global_page_state(NR_SLAB_RECLAIMABLE) + global_page_state(NR_SLAB_UNRECLAIMABLE)), K(global_page_state(NR_SLAB_RECLAIMABLE)), @@ -183,4 +220,4 @@ static int __init proc_meminfo_init(void) proc_create("meminfo", 0, NULL, &meminfo_proc_fops); return 0; } -module_init(proc_meminfo_init); +fs_initcall(proc_meminfo_init); diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c index 9ae46b87470d..89026095f2b5 100644 --- a/fs/proc/namespaces.c +++ b/fs/proc/namespaces.c @@ -146,7 +146,7 @@ static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int bufl struct task_struct *task; void *ns; char name[50]; - int len = -EACCES; + int res = -EACCES; task = get_proc_task(inode); if (!task) @@ -155,24 +155,18 @@ static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int bufl if (!ptrace_may_access(task, PTRACE_MODE_READ)) goto out_put_task; - len = -ENOENT; + res = -ENOENT; ns = ns_ops->get(task); if (!ns) goto out_put_task; snprintf(name, sizeof(name), "%s:[%u]", ns_ops->name, ns_ops->inum(ns)); - len = strlen(name); - - if (len > buflen) - len = buflen; - if (copy_to_user(buffer, name, len)) - len = -EFAULT; - + res = readlink_copy(buffer, buflen, name); ns_ops->put(ns); out_put_task: put_task_struct(task); out: - return len; + return res; } static const struct inode_operations proc_ns_link_inode_operations = { diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c index 5f9bc8a746c9..d4a35746cab9 100644 --- a/fs/proc/nommu.c +++ b/fs/proc/nommu.c @@ -131,4 +131,4 @@ static int __init proc_nommu_init(void) return 0; } -module_init(proc_nommu_init); +fs_initcall(proc_nommu_init); diff --git a/fs/proc/page.c b/fs/proc/page.c index b8730d9ebaee..1e3187da1fed 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -118,10 +118,11 @@ u64 stable_page_flags(struct page *page) /* * PageTransCompound can be true for non-huge compound pages (slab * pages or pages allocated by drivers with __GFP_COMP) because it - * just checks PG_head/PG_tail, so we need to check PageLRU to make - * sure a given page is a thp, not a non-huge compound page. + * just checks PG_head/PG_tail, so we need to check PageLRU/PageAnon + * to make sure a given page is a thp, not a non-huge compound page. */ - else if (PageTransCompound(page) && PageLRU(compound_trans_head(page))) + else if (PageTransCompound(page) && (PageLRU(compound_head(page)) || + PageAnon(compound_head(page)))) u |= 1 << KPF_THP; /* @@ -132,6 +133,9 @@ u64 stable_page_flags(struct page *page) if (PageBuddy(page)) u |= 1 << KPF_BUDDY; + if (PageBalloon(page)) + u |= 1 << KPF_BALLOON; + u |= kpf_copy_bit(k, KPF_LOCKED, PG_locked); u |= kpf_copy_bit(k, KPF_SLAB, PG_slab); @@ -217,4 +221,4 @@ static int __init proc_page_init(void) proc_create("kpageflags", S_IRUSR, NULL, &proc_kpageflags_operations); return 0; } -module_init(proc_page_init); +fs_initcall(proc_page_init); diff --git a/fs/proc/proc_devtree.c b/fs/proc/proc_devtree.c deleted file mode 100644 index 70779b2fc209..000000000000 --- a/fs/proc/proc_devtree.c +++ /dev/null @@ -1,240 +0,0 @@ -/* - * proc_devtree.c - handles /proc/device-tree - * - * Copyright 1997 Paul Mackerras - */ -#include <linux/errno.h> -#include <linux/init.h> -#include <linux/time.h> -#include <linux/proc_fs.h> -#include <linux/seq_file.h> -#include <linux/printk.h> -#include <linux/stat.h> -#include <linux/string.h> -#include <linux/of.h> -#include <linux/export.h> -#include <linux/slab.h> -#include <asm/uaccess.h> -#include "internal.h" - -static inline void set_node_proc_entry(struct device_node *np, - struct proc_dir_entry *de) -{ - np->pde = de; -} - -static struct proc_dir_entry *proc_device_tree; - -/* - * Supply data on a read from /proc/device-tree/node/property. - */ -static int property_proc_show(struct seq_file *m, void *v) -{ - struct property *pp = m->private; - - seq_write(m, pp->value, pp->length); - return 0; -} - -static int property_proc_open(struct inode *inode, struct file *file) -{ - return single_open(file, property_proc_show, __PDE_DATA(inode)); -} - -static const struct file_operations property_proc_fops = { - .owner = THIS_MODULE, - .open = property_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - -/* - * For a node with a name like "gc@10", we make symlinks called "gc" - * and "@10" to it. - */ - -/* - * Add a property to a node - */ -static struct proc_dir_entry * -__proc_device_tree_add_prop(struct proc_dir_entry *de, struct property *pp, - const char *name) -{ - struct proc_dir_entry *ent; - - /* - * Unfortunately proc_register puts each new entry - * at the beginning of the list. So we rearrange them. - */ - ent = proc_create_data(name, - strncmp(name, "security-", 9) ? S_IRUGO : S_IRUSR, - de, &property_proc_fops, pp); - if (ent == NULL) - return NULL; - - if (!strncmp(name, "security-", 9)) - ent->size = 0; /* don't leak number of password chars */ - else - ent->size = pp->length; - - return ent; -} - - -void proc_device_tree_add_prop(struct proc_dir_entry *pde, struct property *prop) -{ - __proc_device_tree_add_prop(pde, prop, prop->name); -} - -void proc_device_tree_remove_prop(struct proc_dir_entry *pde, - struct property *prop) -{ - remove_proc_entry(prop->name, pde); -} - -void proc_device_tree_update_prop(struct proc_dir_entry *pde, - struct property *newprop, - struct property *oldprop) -{ - struct proc_dir_entry *ent; - - if (!oldprop) { - proc_device_tree_add_prop(pde, newprop); - return; - } - - for (ent = pde->subdir; ent != NULL; ent = ent->next) - if (ent->data == oldprop) - break; - if (ent == NULL) { - pr_warn("device-tree: property \"%s\" does not exist\n", - oldprop->name); - } else { - ent->data = newprop; - ent->size = newprop->length; - } -} - -/* - * Various dodgy firmware might give us nodes and/or properties with - * conflicting names. That's generally ok, except for exporting via /proc, - * so munge names here to ensure they're unique. - */ - -static int duplicate_name(struct proc_dir_entry *de, const char *name) -{ - struct proc_dir_entry *ent; - int found = 0; - - spin_lock(&proc_subdir_lock); - - for (ent = de->subdir; ent != NULL; ent = ent->next) { - if (strcmp(ent->name, name) == 0) { - found = 1; - break; - } - } - - spin_unlock(&proc_subdir_lock); - - return found; -} - -static const char *fixup_name(struct device_node *np, struct proc_dir_entry *de, - const char *name) -{ - char *fixed_name; - int fixup_len = strlen(name) + 2 + 1; /* name + #x + \0 */ - int i = 1, size; - -realloc: - fixed_name = kmalloc(fixup_len, GFP_KERNEL); - if (fixed_name == NULL) { - pr_err("device-tree: Out of memory trying to fixup " - "name \"%s\"\n", name); - return name; - } - -retry: - size = snprintf(fixed_name, fixup_len, "%s#%d", name, i); - size++; /* account for NULL */ - - if (size > fixup_len) { - /* We ran out of space, free and reallocate. */ - kfree(fixed_name); - fixup_len = size; - goto realloc; - } - - if (duplicate_name(de, fixed_name)) { - /* Multiple duplicates. Retry with a different offset. */ - i++; - goto retry; - } - - pr_warn("device-tree: Duplicate name in %s, renamed to \"%s\"\n", - np->full_name, fixed_name); - - return fixed_name; -} - -/* - * Process a node, adding entries for its children and its properties. - */ -void proc_device_tree_add_node(struct device_node *np, - struct proc_dir_entry *de) -{ - struct property *pp; - struct proc_dir_entry *ent; - struct device_node *child; - const char *p; - - set_node_proc_entry(np, de); - for (child = NULL; (child = of_get_next_child(np, child));) { - /* Use everything after the last slash, or the full name */ - p = kbasename(child->full_name); - - if (duplicate_name(de, p)) - p = fixup_name(np, de, p); - - ent = proc_mkdir(p, de); - if (ent == NULL) - break; - proc_device_tree_add_node(child, ent); - } - of_node_put(child); - - for (pp = np->properties; pp != NULL; pp = pp->next) { - p = pp->name; - - if (strchr(p, '/')) - continue; - - if (duplicate_name(de, p)) - p = fixup_name(np, de, p); - - ent = __proc_device_tree_add_prop(de, pp, p); - if (ent == NULL) - break; - } -} - -/* - * Called on initialization to set up the /proc/device-tree subtree - */ -void __init proc_device_tree_init(void) -{ - struct device_node *root; - - proc_device_tree = proc_mkdir("device-tree", NULL); - if (proc_device_tree == NULL) - return; - root = of_find_node_by_path("/"); - if (root == NULL) { - pr_debug("/proc/device-tree: can't find root\n"); - return; - } - proc_device_tree_add_node(root, proc_device_tree); - of_node_put(root); -} diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c index 4677bb7dc7c2..a63af3e0a612 100644 --- a/fs/proc/proc_net.c +++ b/fs/proc/proc_net.c @@ -113,9 +113,11 @@ static struct net *get_proc_task_net(struct inode *dir) rcu_read_lock(); task = pid_task(proc_pid(dir), PIDTYPE_PID); if (task != NULL) { - ns = task_nsproxy(task); + task_lock(task); + ns = task->nsproxy; if (ns != NULL) net = get_net(ns->net_ns); + task_unlock(task); } rcu_read_unlock(); diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 71290463a1d3..f92d5dd578a4 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -632,7 +632,7 @@ out: return ret; } -static int scan(struct ctl_table_header *head, ctl_table *table, +static int scan(struct ctl_table_header *head, struct ctl_table *table, unsigned long *pos, struct file *file, struct dir_context *ctx) { diff --git a/fs/proc/proc_tty.c b/fs/proc/proc_tty.c index cb761f010300..15f327bed8c6 100644 --- a/fs/proc/proc_tty.c +++ b/fs/proc/proc_tty.c @@ -18,7 +18,7 @@ /* * The /proc/tty directory inodes... */ -static struct proc_dir_entry *proc_tty_ldisc, *proc_tty_driver; +static struct proc_dir_entry *proc_tty_driver; /* * This is the handler for /proc/tty/drivers @@ -176,7 +176,7 @@ void __init proc_tty_init(void) { if (!proc_mkdir("tty", NULL)) return; - proc_tty_ldisc = proc_mkdir("tty/ldisc", NULL); + proc_mkdir("tty/ldisc", NULL); /* Preserved: it's userspace visible */ /* * /proc/tty/driver/serial reveals the exact character counts for * serial links which is just too easy to abuse for inferring diff --git a/fs/proc/root.c b/fs/proc/root.c index 87dbcbef7fe4..094e44d4a6be 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -92,6 +92,8 @@ static int proc_parse_options(char *options, struct pid_namespace *pid) int proc_remount(struct super_block *sb, int *flags, char *data) { struct pid_namespace *pid = sb->s_fs_info; + + sync_filesystem(sb); return !proc_parse_options(data, pid); } @@ -147,6 +149,8 @@ static void proc_kill_sb(struct super_block *sb) ns = (struct pid_namespace *)sb->s_fs_info; if (ns->proc_self) dput(ns->proc_self); + if (ns->proc_thread_self) + dput(ns->proc_thread_self); kill_anon_super(sb); put_pid_ns(ns); } @@ -168,6 +172,7 @@ void __init proc_root_init(void) return; proc_self_init(); + proc_thread_self_init(); proc_symlink("mounts", NULL, "self/mounts"); proc_net_init(); @@ -183,9 +188,6 @@ void __init proc_root_init(void) proc_mkdir("openprom", NULL); #endif proc_tty_init(); -#ifdef CONFIG_PROC_DEVICETREE - proc_device_tree_init(); -#endif proc_mkdir("bus", NULL); proc_sys_init(); } @@ -200,10 +202,10 @@ static int proc_root_getattr(struct vfsmount *mnt, struct dentry *dentry, struct static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentry, unsigned int flags) { - if (!proc_lookup(dir, dentry, flags)) + if (!proc_pid_lookup(dir, dentry, flags)) return NULL; - return proc_pid_lookup(dir, dentry, flags); + return proc_lookup(dir, dentry, flags); } static int proc_root_readdir(struct file *file, struct dir_context *ctx) diff --git a/fs/proc/self.c b/fs/proc/self.c index ffeb202ec942..4348bb8907c2 100644 --- a/fs/proc/self.c +++ b/fs/proc/self.c @@ -16,7 +16,7 @@ static int proc_self_readlink(struct dentry *dentry, char __user *buffer, if (!tgid) return -ENOENT; sprintf(tmp, "%d", tgid); - return vfs_readlink(dentry,buffer,buflen,tmp); + return readlink_copy(buffer, buflen, tmp); } static void *proc_self_follow_link(struct dentry *dentry, struct nameidata *nd) diff --git a/fs/proc/softirqs.c b/fs/proc/softirqs.c index 62604be9f58d..ad8a77f94beb 100644 --- a/fs/proc/softirqs.c +++ b/fs/proc/softirqs.c @@ -41,4 +41,4 @@ static int __init proc_softirqs_init(void) proc_create("softirqs", 0, NULL, &proc_softirqs_operations); return 0; } -module_init(proc_softirqs_init); +fs_initcall(proc_softirqs_init); diff --git a/fs/proc/stat.c b/fs/proc/stat.c index 1cf86c0e8689..bf2d03f8fd3e 100644 --- a/fs/proc/stat.c +++ b/fs/proc/stat.c @@ -9,7 +9,7 @@ #include <linux/slab.h> #include <linux/time.h> #include <linux/irqnr.h> -#include <asm/cputime.h> +#include <linux/cputime.h> #include <linux/tick.h> #ifndef arch_irq_stat_cpu @@ -184,29 +184,11 @@ static int show_stat(struct seq_file *p, void *v) static int stat_open(struct inode *inode, struct file *file) { - size_t size = 1024 + 128 * num_possible_cpus(); - char *buf; - struct seq_file *m; - int res; + size_t size = 1024 + 128 * num_online_cpus(); /* minimum size to display an interrupt count : 2 bytes */ size += 2 * nr_irqs; - - /* don't ask for more than the kmalloc() max size */ - if (size > KMALLOC_MAX_SIZE) - size = KMALLOC_MAX_SIZE; - buf = kmalloc(size, GFP_KERNEL); - if (!buf) - return -ENOMEM; - - res = single_open(file, show_stat, NULL); - if (!res) { - m = file->private_data; - m->buf = buf; - m->size = ksize(buf); - } else - kfree(buf); - return res; + return single_open_size(file, show_stat, NULL, size); } static const struct file_operations proc_stat_operations = { @@ -221,4 +203,4 @@ static int __init proc_stat_init(void) proc_create("stat", 0, NULL, &proc_stat_operations); return 0; } -module_init(proc_stat_init); +fs_initcall(proc_stat_init); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index fb52b548080d..b7a7dc963a35 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1,4 +1,5 @@ #include <linux/mm.h> +#include <linux/vmacache.h> #include <linux/hugetlb.h> #include <linux/huge_mm.h> #include <linux/mount.h> @@ -86,32 +87,14 @@ unsigned long task_statm(struct mm_struct *mm, #ifdef CONFIG_NUMA /* - * These functions are for numa_maps but called in generic **maps seq_file - * ->start(), ->stop() ops. - * - * numa_maps scans all vmas under mmap_sem and checks their mempolicy. - * Each mempolicy object is controlled by reference counting. The problem here - * is how to avoid accessing dead mempolicy object. - * - * Because we're holding mmap_sem while reading seq_file, it's safe to access - * each vma's mempolicy, no vma objects will never drop refs to mempolicy. - * - * A task's mempolicy (task->mempolicy) has different behavior. task->mempolicy - * is set and replaced under mmap_sem but unrefed and cleared under task_lock(). - * So, without task_lock(), we cannot trust get_vma_policy() because we cannot - * gurantee the task never exits under us. But taking task_lock() around - * get_vma_plicy() causes lock order problem. - * - * To access task->mempolicy without lock, we hold a reference count of an - * object pointed by task->mempolicy and remember it. This will guarantee - * that task->mempolicy points to an alive object or NULL in numa_maps accesses. + * Save get_task_policy() for show_numa_map(). */ static void hold_task_mempolicy(struct proc_maps_private *priv) { struct task_struct *task = priv->task; task_lock(task); - priv->task_mempolicy = task->mempolicy; + priv->task_mempolicy = get_task_policy(task); mpol_get(priv->task_mempolicy); task_unlock(task); } @@ -128,124 +111,154 @@ static void release_task_mempolicy(struct proc_maps_private *priv) } #endif -static void vma_stop(struct proc_maps_private *priv, struct vm_area_struct *vma) +static void vma_stop(struct proc_maps_private *priv) { - if (vma && vma != priv->tail_vma) { - struct mm_struct *mm = vma->vm_mm; - release_task_mempolicy(priv); - up_read(&mm->mmap_sem); - mmput(mm); - } + struct mm_struct *mm = priv->mm; + + release_task_mempolicy(priv); + up_read(&mm->mmap_sem); + mmput(mm); +} + +static struct vm_area_struct * +m_next_vma(struct proc_maps_private *priv, struct vm_area_struct *vma) +{ + if (vma == priv->tail_vma) + return NULL; + return vma->vm_next ?: priv->tail_vma; } -static void *m_start(struct seq_file *m, loff_t *pos) +static void m_cache_vma(struct seq_file *m, struct vm_area_struct *vma) +{ + if (m->count < m->size) /* vma is copied successfully */ + m->version = m_next_vma(m->private, vma) ? vma->vm_start : -1UL; +} + +static void *m_start(struct seq_file *m, loff_t *ppos) { struct proc_maps_private *priv = m->private; unsigned long last_addr = m->version; struct mm_struct *mm; - struct vm_area_struct *vma, *tail_vma = NULL; - loff_t l = *pos; - - /* Clear the per syscall fields in priv */ - priv->task = NULL; - priv->tail_vma = NULL; - - /* - * We remember last_addr rather than next_addr to hit with - * mmap_cache most of the time. We have zero last_addr at - * the beginning and also after lseek. We will have -1 last_addr - * after the end of the vmas. - */ + struct vm_area_struct *vma; + unsigned int pos = *ppos; + /* See m_cache_vma(). Zero at the start or after lseek. */ if (last_addr == -1UL) return NULL; - priv->task = get_pid_task(priv->pid, PIDTYPE_PID); + priv->task = get_proc_task(priv->inode); if (!priv->task) return ERR_PTR(-ESRCH); - mm = mm_access(priv->task, PTRACE_MODE_READ); - if (!mm || IS_ERR(mm)) - return mm; - down_read(&mm->mmap_sem); + mm = priv->mm; + if (!mm || !atomic_inc_not_zero(&mm->mm_users)) + return NULL; - tail_vma = get_gate_vma(priv->task->mm); - priv->tail_vma = tail_vma; + down_read(&mm->mmap_sem); hold_task_mempolicy(priv); - /* Start with last addr hint */ - vma = find_vma(mm, last_addr); - if (last_addr && vma) { - vma = vma->vm_next; - goto out; + priv->tail_vma = get_gate_vma(mm); + + if (last_addr) { + vma = find_vma(mm, last_addr); + if (vma && (vma = m_next_vma(priv, vma))) + return vma; } - /* - * Check the vma index is within the range and do - * sequential scan until m_index. - */ - vma = NULL; - if ((unsigned long)l < mm->map_count) { - vma = mm->mmap; - while (l-- && vma) + m->version = 0; + if (pos < mm->map_count) { + for (vma = mm->mmap; pos; pos--) { + m->version = vma->vm_start; vma = vma->vm_next; - goto out; + } + return vma; } - if (l != mm->map_count) - tail_vma = NULL; /* After gate vma */ - -out: - if (vma) - return vma; + /* we do not bother to update m->version in this case */ + if (pos == mm->map_count && priv->tail_vma) + return priv->tail_vma; - release_task_mempolicy(priv); - /* End of vmas has been reached */ - m->version = (tail_vma != NULL)? 0: -1UL; - up_read(&mm->mmap_sem); - mmput(mm); - return tail_vma; + vma_stop(priv); + return NULL; } static void *m_next(struct seq_file *m, void *v, loff_t *pos) { struct proc_maps_private *priv = m->private; - struct vm_area_struct *vma = v; - struct vm_area_struct *tail_vma = priv->tail_vma; + struct vm_area_struct *next; (*pos)++; - if (vma && (vma != tail_vma) && vma->vm_next) - return vma->vm_next; - vma_stop(priv, vma); - return (vma != tail_vma)? tail_vma: NULL; + next = m_next_vma(priv, v); + if (!next) + vma_stop(priv); + return next; } static void m_stop(struct seq_file *m, void *v) { struct proc_maps_private *priv = m->private; - struct vm_area_struct *vma = v; - if (!IS_ERR(vma)) - vma_stop(priv, vma); - if (priv->task) + if (!IS_ERR_OR_NULL(v)) + vma_stop(priv); + if (priv->task) { put_task_struct(priv->task); + priv->task = NULL; + } +} + +static int proc_maps_open(struct inode *inode, struct file *file, + const struct seq_operations *ops, int psize) +{ + struct proc_maps_private *priv = __seq_open_private(file, ops, psize); + + if (!priv) + return -ENOMEM; + + priv->inode = inode; + priv->mm = proc_mem_open(inode, PTRACE_MODE_READ); + if (IS_ERR(priv->mm)) { + int err = PTR_ERR(priv->mm); + + seq_release_private(inode, file); + return err; + } + + return 0; +} + +static int proc_map_release(struct inode *inode, struct file *file) +{ + struct seq_file *seq = file->private_data; + struct proc_maps_private *priv = seq->private; + + if (priv->mm) + mmdrop(priv->mm); + + return seq_release_private(inode, file); } static int do_maps_open(struct inode *inode, struct file *file, const struct seq_operations *ops) { - struct proc_maps_private *priv; - int ret = -ENOMEM; - priv = kzalloc(sizeof(*priv), GFP_KERNEL); - if (priv) { - priv->pid = proc_pid(inode); - ret = seq_open(file, ops); - if (!ret) { - struct seq_file *m = file->private_data; - m->private = priv; - } else { - kfree(priv); - } + return proc_maps_open(inode, file, ops, + sizeof(struct proc_maps_private)); +} + +static pid_t pid_of_stack(struct proc_maps_private *priv, + struct vm_area_struct *vma, bool is_pid) +{ + struct inode *inode = priv->inode; + struct task_struct *task; + pid_t ret = 0; + + rcu_read_lock(); + task = pid_task(proc_pid(inode), PIDTYPE_PID); + if (task) { + task = task_of_stack(task, vma, is_pid); + if (task) + ret = task_pid_nr_ns(task, inode->i_sb->s_fs_info); } + rcu_read_unlock(); + return ret; } @@ -255,7 +268,6 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid) struct mm_struct *mm = vma->vm_mm; struct file *file = vma->vm_file; struct proc_maps_private *priv = m->private; - struct task_struct *task = priv->task; vm_flags_t flags = vma->vm_flags; unsigned long ino = 0; unsigned long long pgoff = 0; @@ -299,6 +311,12 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid) goto done; } + if (vma->vm_ops && vma->vm_ops->name) { + name = vma->vm_ops->name(vma); + if (name) + goto done; + } + name = arch_vma_name(vma); if (!name) { pid_t tid; @@ -314,8 +332,7 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid) goto done; } - tid = vm_is_stack(task, vma, is_pid); - + tid = pid_of_stack(priv, vma, is_pid); if (tid != 0) { /* * Thread stack in /proc/PID/task/TID/maps or @@ -342,15 +359,8 @@ done: static int show_map(struct seq_file *m, void *v, int is_pid) { - struct vm_area_struct *vma = v; - struct proc_maps_private *priv = m->private; - struct task_struct *task = priv->task; - - show_map_vma(m, vma, is_pid); - - if (m->count < m->size) /* vma is copied successfully */ - m->version = (vma != get_gate_vma(task->mm)) - ? vma->vm_start : 0; + show_map_vma(m, v, is_pid); + m_cache_vma(m, v); return 0; } @@ -392,14 +402,14 @@ const struct file_operations proc_pid_maps_operations = { .open = pid_maps_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release_private, + .release = proc_map_release, }; const struct file_operations proc_tid_maps_operations = { .open = tid_maps_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release_private, + .release = proc_map_release, }; /* @@ -576,8 +586,6 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) static int show_smap(struct seq_file *m, void *v, int is_pid) { - struct proc_maps_private *priv = m->private; - struct task_struct *task = priv->task; struct vm_area_struct *vma = v; struct mem_size_stats mss; struct mm_walk smaps_walk = { @@ -630,10 +638,7 @@ static int show_smap(struct seq_file *m, void *v, int is_pid) mss.nonlinear >> 10); show_smap_vma_flags(m, vma); - - if (m->count < m->size) /* vma is copied successfully */ - m->version = (vma != get_gate_vma(task->mm)) - ? vma->vm_start : 0; + m_cache_vma(m, vma); return 0; } @@ -675,14 +680,14 @@ const struct file_operations proc_pid_smaps_operations = { .open = pid_smaps_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release_private, + .release = proc_map_release, }; const struct file_operations proc_tid_smaps_operations = { .open = tid_smaps_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release_private, + .release = proc_map_release, }; /* @@ -736,9 +741,6 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma, ptent = pte_file_clear_soft_dirty(ptent); } - if (vma->vm_flags & VM_SOFTDIRTY) - vma->vm_flags &= ~VM_SOFTDIRTY; - set_pte_at(vma->vm_mm, addr, pte, ptent); #endif } @@ -806,8 +808,9 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, if (type == CLEAR_REFS_SOFT_DIRTY) { soft_dirty_cleared = true; - pr_warn_once("The pagemap bits 55-60 has changed their meaning! " - "See the linux/Documentation/vm/pagemap.txt for details.\n"); + pr_warn_once("The pagemap bits 55-60 has changed their meaning!" + " See the linux/Documentation/vm/pagemap.txt for " + "details.\n"); } task = get_proc_task(file_inode(file)); @@ -838,11 +841,17 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, * * Writing 3 to /proc/pid/clear_refs only affects file * mapped pages. + * + * Writing 4 to /proc/pid/clear_refs affects all pages. */ if (type == CLEAR_REFS_ANON && vma->vm_file) continue; if (type == CLEAR_REFS_MAPPED && !vma->vm_file) continue; + if (type == CLEAR_REFS_SOFT_DIRTY) { + if (vma->vm_flags & VM_SOFTDIRTY) + vma->vm_flags &= ~VM_SOFTDIRTY; + } walk_page_range(vma->vm_start, vma->vm_end, &clear_refs_walk); } @@ -914,15 +923,39 @@ static int pagemap_pte_hole(unsigned long start, unsigned long end, struct mm_walk *walk) { struct pagemapread *pm = walk->private; - unsigned long addr; + unsigned long addr = start; int err = 0; - pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2)); - for (addr = start; addr < end; addr += PAGE_SIZE) { - err = add_to_pagemap(addr, &pme, pm); - if (err) + while (addr < end) { + struct vm_area_struct *vma = find_vma(walk->mm, addr); + pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2)); + /* End of address space hole, which we mark as non-present. */ + unsigned long hole_end; + + if (vma) + hole_end = min(end, vma->vm_start); + else + hole_end = end; + + for (; addr < hole_end; addr += PAGE_SIZE) { + err = add_to_pagemap(addr, &pme, pm); + if (err) + goto out; + } + + if (!vma) break; + + /* Addresses in the VMA. */ + if (vma->vm_flags & VM_SOFTDIRTY) + pme.pme |= PM_STATUS2(pm->v2, __PM_SOFT_DIRTY); + for (; addr < min(end, vma->vm_end); addr += PAGE_SIZE) { + err = add_to_pagemap(addr, &pme, pm); + if (err) + goto out; + } } +out: return err; } @@ -994,7 +1027,6 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, spinlock_t *ptl; pte_t *pte; int err = 0; - pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2)); /* find the first VMA at or above 'addr' */ vma = find_vma(walk->mm, addr); @@ -1008,6 +1040,7 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, for (; addr != end; addr += PAGE_SIZE) { unsigned long offset; + pagemap_entry_t pme; offset = (addr & ~PAGEMAP_WALK_MASK) >> PAGE_SHIFT; @@ -1022,32 +1055,51 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, if (pmd_trans_unstable(pmd)) return 0; - for (; addr != end; addr += PAGE_SIZE) { - int flags2; - - /* check to see if we've left 'vma' behind - * and need a new, higher one */ - if (vma && (addr >= vma->vm_end)) { - vma = find_vma(walk->mm, addr); - if (vma && (vma->vm_flags & VM_SOFTDIRTY)) - flags2 = __PM_SOFT_DIRTY; - else - flags2 = 0; - pme = make_pme(PM_NOT_PRESENT(pm->v2) | PM_STATUS2(pm->v2, flags2)); + + while (1) { + /* End of address space hole, which we mark as non-present. */ + unsigned long hole_end; + + if (vma) + hole_end = min(end, vma->vm_start); + else + hole_end = end; + + for (; addr < hole_end; addr += PAGE_SIZE) { + pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2)); + + err = add_to_pagemap(addr, &pme, pm); + if (err) + return err; } - /* check that 'vma' actually covers this address, - * and that it isn't a huge page vma */ - if (vma && (vma->vm_start <= addr) && - !is_vm_hugetlb_page(vma)) { + if (!vma || vma->vm_start >= end) + break; + /* + * We can't possibly be in a hugetlb VMA. In general, + * for a mm_walk with a pmd_entry and a hugetlb_entry, + * the pmd_entry can only be called on addresses in a + * hugetlb if the walk starts in a non-hugetlb VMA and + * spans a hugepage VMA. Since pagemap_read walks are + * PMD-sized and PMD-aligned, this will never be true. + */ + BUG_ON(is_vm_hugetlb_page(vma)); + + /* Addresses in the VMA. */ + for (; addr < min(end, vma->vm_end); addr += PAGE_SIZE) { + pagemap_entry_t pme; pte = pte_offset_map(pmd, addr); pte_to_pagemap_entry(&pme, pm, vma, addr, *pte); - /* unmap before userspace copy */ pte_unmap(pte); + err = add_to_pagemap(addr, &pme, pm); + if (err) + return err; } - err = add_to_pagemap(addr, &pme, pm); - if (err) - return err; + + if (addr == end) + break; + + vma = find_vma(walk->mm, addr); } cond_resched(); @@ -1350,7 +1402,7 @@ static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask, struct numa_maps *md; struct page *page; - if (pte_none(*pte)) + if (!pte_present(*pte)) return 0; page = pte_page(*pte); @@ -1380,7 +1432,6 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid) struct vm_area_struct *vma = v; struct numa_maps *md = &numa_priv->md; struct file *file = vma->vm_file; - struct task_struct *task = proc_priv->task; struct mm_struct *mm = vma->vm_mm; struct mm_walk walk = {}; struct mempolicy *pol; @@ -1400,19 +1451,23 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid) walk.private = md; walk.mm = mm; - pol = get_vma_policy(task, vma, vma->vm_start); - mpol_to_str(buffer, sizeof(buffer), pol); - mpol_cond_put(pol); + pol = __get_vma_policy(vma, vma->vm_start); + if (pol) { + mpol_to_str(buffer, sizeof(buffer), pol); + mpol_cond_put(pol); + } else { + mpol_to_str(buffer, sizeof(buffer), proc_priv->task_mempolicy); + } seq_printf(m, "%08lx %s", vma->vm_start, buffer); if (file) { - seq_printf(m, " file="); + seq_puts(m, " file="); seq_path(m, &file->f_path, "\n\t= "); } else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) { - seq_printf(m, " heap"); + seq_puts(m, " heap"); } else { - pid_t tid = vm_is_stack(task, vma, is_pid); + pid_t tid = pid_of_stack(proc_priv, vma, is_pid); if (tid != 0) { /* * Thread stack in /proc/PID/task/TID/maps or @@ -1420,14 +1475,14 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid) */ if (!is_pid || (vma->vm_start <= mm->start_stack && vma->vm_end >= mm->start_stack)) - seq_printf(m, " stack"); + seq_puts(m, " stack"); else seq_printf(m, " stack:%d", tid); } } if (is_vm_hugetlb_page(vma)) - seq_printf(m, " huge"); + seq_puts(m, " huge"); walk_page_range(vma->vm_start, vma->vm_end, &walk); @@ -1460,9 +1515,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid) seq_printf(m, " N%d=%lu", nid, md->node[nid]); out: seq_putc(m, '\n'); - - if (m->count < m->size) - m->version = (vma != proc_priv->tail_vma) ? vma->vm_start : 0; + m_cache_vma(m, vma); return 0; } @@ -1493,20 +1546,8 @@ static const struct seq_operations proc_tid_numa_maps_op = { static int numa_maps_open(struct inode *inode, struct file *file, const struct seq_operations *ops) { - struct numa_maps_private *priv; - int ret = -ENOMEM; - priv = kzalloc(sizeof(*priv), GFP_KERNEL); - if (priv) { - priv->proc_maps.pid = proc_pid(inode); - ret = seq_open(file, ops); - if (!ret) { - struct seq_file *m = file->private_data; - m->private = priv; - } else { - kfree(priv); - } - } - return ret; + return proc_maps_open(inode, file, ops, + sizeof(struct numa_maps_private)); } static int pid_numa_maps_open(struct inode *inode, struct file *file) @@ -1523,13 +1564,13 @@ const struct file_operations proc_pid_numa_maps_operations = { .open = pid_numa_maps_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release_private, + .release = proc_map_release, }; const struct file_operations proc_tid_numa_maps_operations = { .open = tid_numa_maps_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release_private, + .release = proc_map_release, }; #endif /* CONFIG_NUMA */ diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index 678455d2d683..599ec2e20104 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -123,6 +123,25 @@ unsigned long task_statm(struct mm_struct *mm, return size; } +static pid_t pid_of_stack(struct proc_maps_private *priv, + struct vm_area_struct *vma, bool is_pid) +{ + struct inode *inode = priv->inode; + struct task_struct *task; + pid_t ret = 0; + + rcu_read_lock(); + task = pid_task(proc_pid(inode), PIDTYPE_PID); + if (task) { + task = task_of_stack(task, vma, is_pid); + if (task) + ret = task_pid_nr_ns(task, inode->i_sb->s_fs_info); + } + rcu_read_unlock(); + + return ret; +} + /* * display a single VMA to a sequenced file */ @@ -163,7 +182,7 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma, seq_pad(m, ' '); seq_path(m, &file->f_path, ""); } else if (mm) { - pid_t tid = vm_is_stack(priv->task, vma, is_pid); + pid_t tid = pid_of_stack(priv, vma, is_pid); if (tid != 0) { seq_pad(m, ' '); @@ -212,22 +231,22 @@ static void *m_start(struct seq_file *m, loff_t *pos) loff_t n = *pos; /* pin the task and mm whilst we play with them */ - priv->task = get_pid_task(priv->pid, PIDTYPE_PID); + priv->task = get_proc_task(priv->inode); if (!priv->task) return ERR_PTR(-ESRCH); - mm = mm_access(priv->task, PTRACE_MODE_READ); - if (!mm || IS_ERR(mm)) { - put_task_struct(priv->task); - priv->task = NULL; - return mm; - } - down_read(&mm->mmap_sem); + mm = priv->mm; + if (!mm || !atomic_inc_not_zero(&mm->mm_users)) + return NULL; + down_read(&mm->mmap_sem); /* start from the Nth VMA */ for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) if (n-- == 0) return p; + + up_read(&mm->mmap_sem); + mmput(mm); return NULL; } @@ -235,11 +254,13 @@ static void m_stop(struct seq_file *m, void *_vml) { struct proc_maps_private *priv = m->private; + if (!IS_ERR_OR_NULL(_vml)) { + up_read(&priv->mm->mmap_sem); + mmput(priv->mm); + } if (priv->task) { - struct mm_struct *mm = priv->task->mm; - up_read(&mm->mmap_sem); - mmput(mm); put_task_struct(priv->task); + priv->task = NULL; } } @@ -269,20 +290,33 @@ static int maps_open(struct inode *inode, struct file *file, const struct seq_operations *ops) { struct proc_maps_private *priv; - int ret = -ENOMEM; - - priv = kzalloc(sizeof(*priv), GFP_KERNEL); - if (priv) { - priv->pid = proc_pid(inode); - ret = seq_open(file, ops); - if (!ret) { - struct seq_file *m = file->private_data; - m->private = priv; - } else { - kfree(priv); - } + + priv = __seq_open_private(file, ops, sizeof(*priv)); + if (!priv) + return -ENOMEM; + + priv->inode = inode; + priv->mm = proc_mem_open(inode, PTRACE_MODE_READ); + if (IS_ERR(priv->mm)) { + int err = PTR_ERR(priv->mm); + + seq_release_private(inode, file); + return err; } - return ret; + + return 0; +} + + +static int map_release(struct inode *inode, struct file *file) +{ + struct seq_file *seq = file->private_data; + struct proc_maps_private *priv = seq->private; + + if (priv->mm) + mmdrop(priv->mm); + + return seq_release_private(inode, file); } static int pid_maps_open(struct inode *inode, struct file *file) @@ -299,13 +333,13 @@ const struct file_operations proc_pid_maps_operations = { .open = pid_maps_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release_private, + .release = map_release, }; const struct file_operations proc_tid_maps_operations = { .open = tid_maps_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release_private, + .release = map_release, }; diff --git a/fs/proc/thread_self.c b/fs/proc/thread_self.c new file mode 100644 index 000000000000..59075b509df3 --- /dev/null +++ b/fs/proc/thread_self.c @@ -0,0 +1,85 @@ +#include <linux/sched.h> +#include <linux/namei.h> +#include <linux/slab.h> +#include <linux/pid_namespace.h> +#include "internal.h" + +/* + * /proc/thread_self: + */ +static int proc_thread_self_readlink(struct dentry *dentry, char __user *buffer, + int buflen) +{ + struct pid_namespace *ns = dentry->d_sb->s_fs_info; + pid_t tgid = task_tgid_nr_ns(current, ns); + pid_t pid = task_pid_nr_ns(current, ns); + char tmp[PROC_NUMBUF + 6 + PROC_NUMBUF]; + if (!pid) + return -ENOENT; + sprintf(tmp, "%d/task/%d", tgid, pid); + return readlink_copy(buffer, buflen, tmp); +} + +static void *proc_thread_self_follow_link(struct dentry *dentry, struct nameidata *nd) +{ + struct pid_namespace *ns = dentry->d_sb->s_fs_info; + pid_t tgid = task_tgid_nr_ns(current, ns); + pid_t pid = task_pid_nr_ns(current, ns); + char *name = ERR_PTR(-ENOENT); + if (pid) { + name = kmalloc(PROC_NUMBUF + 6 + PROC_NUMBUF, GFP_KERNEL); + if (!name) + name = ERR_PTR(-ENOMEM); + else + sprintf(name, "%d/task/%d", tgid, pid); + } + nd_set_link(nd, name); + return NULL; +} + +static const struct inode_operations proc_thread_self_inode_operations = { + .readlink = proc_thread_self_readlink, + .follow_link = proc_thread_self_follow_link, + .put_link = kfree_put_link, +}; + +static unsigned thread_self_inum; + +int proc_setup_thread_self(struct super_block *s) +{ + struct inode *root_inode = s->s_root->d_inode; + struct pid_namespace *ns = s->s_fs_info; + struct dentry *thread_self; + + mutex_lock(&root_inode->i_mutex); + thread_self = d_alloc_name(s->s_root, "thread-self"); + if (thread_self) { + struct inode *inode = new_inode_pseudo(s); + if (inode) { + inode->i_ino = thread_self_inum; + inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; + inode->i_mode = S_IFLNK | S_IRWXUGO; + inode->i_uid = GLOBAL_ROOT_UID; + inode->i_gid = GLOBAL_ROOT_GID; + inode->i_op = &proc_thread_self_inode_operations; + d_add(thread_self, inode); + } else { + dput(thread_self); + thread_self = ERR_PTR(-ENOMEM); + } + } else { + thread_self = ERR_PTR(-ENOMEM); + } + mutex_unlock(&root_inode->i_mutex); + if (IS_ERR(thread_self)) { + pr_err("proc_fill_super: can't allocate /proc/thread_self\n"); + return PTR_ERR(thread_self); + } + ns->proc_thread_self = thread_self; + return 0; +} + +void __init proc_thread_self_init(void) +{ + proc_alloc_inum(&thread_self_inum); +} diff --git a/fs/proc/uptime.c b/fs/proc/uptime.c index 061894625903..33de567c25af 100644 --- a/fs/proc/uptime.c +++ b/fs/proc/uptime.c @@ -5,7 +5,7 @@ #include <linux/seq_file.h> #include <linux/time.h> #include <linux/kernel_stat.h> -#include <asm/cputime.h> +#include <linux/cputime.h> static int uptime_proc_show(struct seq_file *m, void *v) { @@ -49,4 +49,4 @@ static int __init proc_uptime_init(void) proc_create("uptime", 0, NULL, &uptime_proc_fops); return 0; } -module_init(proc_uptime_init); +fs_initcall(proc_uptime_init); diff --git a/fs/proc/version.c b/fs/proc/version.c index 76817a60678c..d2154eb6d78f 100644 --- a/fs/proc/version.c +++ b/fs/proc/version.c @@ -31,4 +31,4 @@ static int __init proc_version_init(void) proc_create("version", 0, NULL, &version_proc_fops); return 0; } -module_init(proc_version_init); +fs_initcall(proc_version_init); diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 9100d6959886..a90d6d354199 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -42,7 +42,7 @@ static size_t elfnotes_sz; /* Total size of vmcore file. */ static u64 vmcore_size; -static struct proc_dir_entry *proc_vmcore = NULL; +static struct proc_dir_entry *proc_vmcore; /* * Returns > 0 for RAM pages, 0 for non-RAM pages, < 0 on error @@ -328,6 +328,82 @@ static inline char *alloc_elfnotes_buf(size_t notes_sz) * virtually contiguous user-space in ELF layout. */ #ifdef CONFIG_MMU +/* + * remap_oldmem_pfn_checked - do remap_oldmem_pfn_range replacing all pages + * reported as not being ram with the zero page. + * + * @vma: vm_area_struct describing requested mapping + * @from: start remapping from + * @pfn: page frame number to start remapping to + * @size: remapping size + * @prot: protection bits + * + * Returns zero on success, -EAGAIN on failure. + */ +static int remap_oldmem_pfn_checked(struct vm_area_struct *vma, + unsigned long from, unsigned long pfn, + unsigned long size, pgprot_t prot) +{ + unsigned long map_size; + unsigned long pos_start, pos_end, pos; + unsigned long zeropage_pfn = my_zero_pfn(0); + size_t len = 0; + + pos_start = pfn; + pos_end = pfn + (size >> PAGE_SHIFT); + + for (pos = pos_start; pos < pos_end; ++pos) { + if (!pfn_is_ram(pos)) { + /* + * We hit a page which is not ram. Remap the continuous + * region between pos_start and pos-1 and replace + * the non-ram page at pos with the zero page. + */ + if (pos > pos_start) { + /* Remap continuous region */ + map_size = (pos - pos_start) << PAGE_SHIFT; + if (remap_oldmem_pfn_range(vma, from + len, + pos_start, map_size, + prot)) + goto fail; + len += map_size; + } + /* Remap the zero page */ + if (remap_oldmem_pfn_range(vma, from + len, + zeropage_pfn, + PAGE_SIZE, prot)) + goto fail; + len += PAGE_SIZE; + pos_start = pos + 1; + } + } + if (pos > pos_start) { + /* Remap the rest */ + map_size = (pos - pos_start) << PAGE_SHIFT; + if (remap_oldmem_pfn_range(vma, from + len, pos_start, + map_size, prot)) + goto fail; + } + return 0; +fail: + do_munmap(vma->vm_mm, from, len); + return -EAGAIN; +} + +static int vmcore_remap_oldmem_pfn(struct vm_area_struct *vma, + unsigned long from, unsigned long pfn, + unsigned long size, pgprot_t prot) +{ + /* + * Check if oldmem_pfn_is_ram was registered to avoid + * looping over all pages without a reason. + */ + if (oldmem_pfn_is_ram) + return remap_oldmem_pfn_checked(vma, from, pfn, size, prot); + else + return remap_oldmem_pfn_range(vma, from, pfn, size, prot); +} + static int mmap_vmcore(struct file *file, struct vm_area_struct *vma) { size_t size = vma->vm_end - vma->vm_start; @@ -387,9 +463,9 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma) tsz = min_t(size_t, m->offset + m->size - start, size); paddr = m->paddr + start - m->offset; - if (remap_oldmem_pfn_range(vma, vma->vm_start + len, - paddr >> PAGE_SHIFT, tsz, - vma->vm_page_prot)) + if (vmcore_remap_oldmem_pfn(vma, vma->vm_start + len, + paddr >> PAGE_SHIFT, tsz, + vma->vm_page_prot)) goto fail; size -= tsz; start += tsz; @@ -468,17 +544,23 @@ static int __init update_note_header_size_elf64(const Elf64_Ehdr *ehdr_ptr) return rc; } nhdr_ptr = notes_section; - while (real_sz < max_sz) { - if (nhdr_ptr->n_namesz == 0) - break; + while (nhdr_ptr->n_namesz != 0) { sz = sizeof(Elf64_Nhdr) + ((nhdr_ptr->n_namesz + 3) & ~3) + ((nhdr_ptr->n_descsz + 3) & ~3); + if ((real_sz + sz) > max_sz) { + pr_warn("Warning: Exceeded p_memsz, dropping PT_NOTE entry n_namesz=0x%x, n_descsz=0x%x\n", + nhdr_ptr->n_namesz, nhdr_ptr->n_descsz); + break; + } real_sz += sz; nhdr_ptr = (Elf64_Nhdr*)((char*)nhdr_ptr + sz); } kfree(notes_section); phdr_ptr->p_memsz = real_sz; + if (real_sz == 0) { + pr_warn("Warning: Zero PT_NOTE entries found\n"); + } } return 0; @@ -648,17 +730,23 @@ static int __init update_note_header_size_elf32(const Elf32_Ehdr *ehdr_ptr) return rc; } nhdr_ptr = notes_section; - while (real_sz < max_sz) { - if (nhdr_ptr->n_namesz == 0) - break; + while (nhdr_ptr->n_namesz != 0) { sz = sizeof(Elf32_Nhdr) + ((nhdr_ptr->n_namesz + 3) & ~3) + ((nhdr_ptr->n_descsz + 3) & ~3); + if ((real_sz + sz) > max_sz) { + pr_warn("Warning: Exceeded p_memsz, dropping PT_NOTE entry n_namesz=0x%x, n_descsz=0x%x\n", + nhdr_ptr->n_namesz, nhdr_ptr->n_descsz); + break; + } real_sz += sz; nhdr_ptr = (Elf32_Nhdr*)((char*)nhdr_ptr + sz); } kfree(notes_section); phdr_ptr->p_memsz = real_sz; + if (real_sz == 0) { + pr_warn("Warning: Zero PT_NOTE entries found\n"); + } } return 0; @@ -1082,7 +1170,7 @@ static int __init vmcore_init(void) proc_vmcore->size = vmcore_size; return 0; } -module_init(vmcore_init) +fs_initcall(vmcore_init); /* Cleanup function for vmcore module. */ void vmcore_cleanup(void) @@ -1104,4 +1192,3 @@ void vmcore_cleanup(void) } free_elfcorebuf(); } -EXPORT_SYMBOL_GPL(vmcore_cleanup); |